Skills
Navigate
skills/frostney/known-good-route/native-nostalgia-stack/Gen Agent Trust Hub

native-nostalgia-stack

Pass

Audited by Gen Agent Trust Hub on Sep 28, 2026

Risk Level: SAFEINDIRECT_PROMPT_INJECTIONCOMMAND_EXECUTION
Full Analysis
  • [INDIRECT_PROMPT_INJECTION]: The skill directs the agent to ingest and follow instructions from external project-level sources, creating a potential attack surface.
  • Ingestion points: SKILL.md instructs the agent to "inspect root and area AGENTS" and read documentation files such as docs/build-system.md, docs/tooling.md, and docs/code-style.md.
  • Boundary markers: The instructions do not specify the use of delimiters or provide warnings to ignore instructions embedded within these project files.
  • Capability inventory: The skill assumes capabilities to execute compiler commands (fpc), script runners (InstantFPC), and hook managers (Lefthook).
  • Sanitization: There is no mention of sanitizing or validating the contents of the ingested project files.
  • [COMMAND_EXECUTION]: The skill defines a workflow requiring the execution of shell-based development tools.
  • The agent is instructed to use the FreePascal compiler (fpc), the Lefthook utility for pre-commit hooks, and project-specific build entry points for compilation and testing.
Audit Metadata
Risk Level
SAFE
Analyzed
Sep 28, 2026, 04:17 PM